Deborah L. Mcguinness Explaining Complex Systems

Explaining Complex Systems Deborah L. McGuinness Acting Director Knowledge Systems, AI Lab, Stanford University Tetherless World Chair, Rensselaer Polytechnic Institute (RPI)

Increasing Explanation Motivations 



Systems are getting more complex  Multiple heterogeneous distributed information sources  Highly variable reliability of information sources  Interest in reuse of information systems (many times for purposes other than those originally planned for)  Hybrid and distributed processing  Multiple types of components, including multiple learners (e.g., calo, gila), multiple text components (e.g., uima, kani, …)  Less transparency of system computation and reasoning Systems are taking more autonomous control  Guide/assist user actions  Perform autonomous actions on behalf of user  “reason, learn from experience, be told what to do, explain what they are doing, reflect on their experience, and respond robustly to surprise” *

* DARPA PAL program: Deborah L. McGuinness

http://www.darpa.mil/ipto/programs/pal/ Semantic e-Science Vancouver July 23, 2007

2

Motivation Support explanations of provenance, information manipulation trace, and trust using an interoperable, transparent, and user-friendly knowledge provenance infrastructure. 

Explanation 











Provenance – if users (humans and agents) are to use and integrate data from unknown, unreliable, or evolving sources, they need provenance metadata for evaluation Information manipulation trace – if information has been manipulated (i.e., by sound deduction or by heuristic processes), information manipulation trace information should be available Trust – if some sources are more trustworthy than others, representations should be available to encode, propagate, combine, and (appropriately) display trust values

Interoperability – as systems use varied sources and multiple information manipulation engines, they benefit more from encodings that are shareable & interoperable Transparency –explanations can be used to provide transparency and accountability for systems by allowing (authorized) users to see what the system has done.. Usability – varied users need rich representation options and a broad range of tool support to provide context- and user-appropriate presentations. Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

3

Inference Web Explanation Infrastructure WWW

SDS

OWL-S/BPEL

Trace of web service discovery

CWM

N3

Proof Markup Language (PML)

KIF

Trust

Toolkit IWTrust IW Explainer/ Abstractor

Trace of rule application

JTP Trace of theorem prover

SPARK

SPARK-L

Trace of task execution

UIMA

Justification Provenance

Text Analytics

Trust computation End-user friendly visualization

IWBrowser

Expert friendly Visualization

IWSearch

search engine based publishing

IWBase

provenance registration

Trace of information extraction

 

Semantic Web based infrastructure PML is an explanation interlingua  



Represent knowledge provenance (who, where, when…) Represent justifications and workflow traces across system boundaries

Inference Web provides a toolkit for data management and visualization Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

4

Explaining Information Manipulation in PML (behind the scenes) Question - foo:question1 “when and where does Ramazi have an office” Query - foo:query1 “(Holds (|hasOffice| |Ramazi| ?where) ?when) ” isQueryFor

IWRegistry (Provenance Metadata)

hasAnswer hasLanguage NodeSet - foo:ns1 {answer to query} “(Holds (|hasOffice| |Ramazi| |SelectGourmetFoods|) April_01_2003)”

Language - reg:KIF

isConsequentOf fromQuery

hasInferencEngine

InferenceStep hasAntecendent

InferenceEngine - reg:JTP

hasInferenceRule

hasVariableMapping Mapping From: “?f”

InferenceRule - reg:GMP

To: “(|hasOffice| |Ramazi| ?where)”

More mappings …

Source – reg:TypicalityOnto

More NodeSets…

NodeSet - foo:ns2 {direct assertion} “(<= (or (Ab ?f ?t) (Holds ?f ?t)) (Holds* ?f ?t))” fromAnswer InferenceStep Deborah L. McGuinness

isConsequentOf hasSourceUsage

SourceUsage

hasSource Semantic e-Science Vancouver July 23, 2007

5

Filtered View Views of Explanation filtered

focused

Explanation (in PML)

trust



abstraction discourse

provenance

Show Highlights   



Deborah L. McGuinness

global

Query Answer Supporting assertions Sources

Semantic e-Science Vancouver July 23, 2007

6

Focused View Views of Explanation filtered

focused

Explanation (in PML)

trust



  

discourse provenance

Original query Conclusion Direct antecedents Inference rule

Contextually appropriate follow-up questions      

Deborah L. McGuinness

abstraction

One step of justification 



global

Sources Ground Assertions Assumptions Full trace Question answerers used …

Semantic e-Science Vancouver July 23, 2007

7

Global View and More Views of Explanation filtered

focused

Explanation (in PML)



provenance

Explanation as a graph Customizable browser options    



Proof style Sentence format Lens magnitude Lens width

More information     

Deborah L. McGuinness

abstraction discourse

trust



global



Provenance metadata Source PML Proof statistics Variable bindings Link to tabulator …

Semantic e-Science Vancouver July 23, 2007

8

Abstraction View 

Rewrite rules used to hide part(s) of the sub-graph

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

9

Discourse View    

(Limited) natural language interface Mixed initiative dialogue Exemplified in CALO domain Explains task execution component powered by learned and human generated procedures

Deborah L. McGuinness

Views of Explanation filtered

focused

Explanation (in PML)

trust

global abstraction discourse

provenance

Semantic e-Science Vancouver July 23, 2007

10

Provenance View  

Source metadata: name, description, … Source-Usage metadata: which fragment of a source has been used when

Views of Explanation filtered

focused

Explanation (in PML)

trust

Deborah L. McGuinness

global abstraction discourse

provenance

Semantic e-Science Vancouver July 23, 2007

11

Trust View Views of Explanation filtered Detailed trust explanation

Trust Tab

Explanation (in PML)

trust

 



Fragment colored by trust value Deborah L. McGuinness

focused

global abstraction discourse

provenance

(preliminary) simple trust representation Provides colored (mouseable) view based on trust values Enables sharing and collaborative computation and propagation of trust values

Semantic e-Science Vancouver July 23, 2007

12

Inference Web Data Access Interface 

Browse   



Organized by class-hierarchy Customized entry Summary and audit views (in report listing)

Search (with filters) 

NodeSet 

  

Deborah L. McGuinness

root NodeSet

Query Conclusion …

Semantic e-Science Vancouver July 23, 2007

13

The Use-Ask-Understand-Update Cycle

Use

Update

Deborah L. McGuinness

Ask

Understand / Accept

Semantic e-Science Vancouver July 23, 2007

14

Selected IW and PML Applications 

        

Portable proofs across reasoners: JTP (with temporal and context reasoners (Stanford); CWM (W3C), SNARK(SRI), … Explaining web service composition and discovery (SNRC) Explaining information extraction (more emphasis on provenance – KANI, UIMA) Explaining intelligence analysts’ tools (NIMD/KANI) Explaining tasks processing (SPARK / CALO) Explaining learned procedures (TAILOR, LAPDOG, / CALO) Explaining privacy policy law validation (TAMI) Explaining decision making and machine learning (GILA) Explaining trust in social collaborative networks (TrustTab) Registered knowledge provenance: IW Registrar (Explainable Knowledge Aggregation) Deborah L. McGuinness Semantic e-Science Vancouver July 23, 2007

15

Trend: Semantically Enabling Applications leveraging the Semantic Web focus

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

16

Semantic Web Methodology and Technology Development Process 

Open World: Evolve, Iterate, Redesign, Redeploy

Establish and improve a well-defined methodology vision for Semantic Technology-based application development

Rapid Prototype

Leverage Technology Infrastructure

Adopt Technology Approach

Expert Review & Iteration

Use Tools Analysis

Use Case

Small Team, mixed skills Deborah L. McGuinness

Develop model/ ontology Joint with P. Fox

Semantic e-Science Vancouver July 23, 2007

17

Scientific Environment Goal Scientists should be able to access a global, distributed knowledge base of scientific data that: • appears to be integrated • appears to be locally available But… data is obtained by multiple instruments, using various protocols, in differing vocabularies, using (sometimes unstated) assumptions, with inconsistent (or non-existent) meta-data. It may be inconsistent, incomplete, evolving, and distributed.

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

18

Virtual Observatory 

Workshop: A Virtual Observatory (VO) is a suite of software applications on a set of computers that allows users to uniformly find, access, and use resources (data, software, document, and image products and services using these) from a collection of distributed product repositories and service providers. A VO is a service that unites services and/or multiple repositories. lwsde.gsfc.nasa.gov/VO_Framework_7_Jan_05.doc

 

VxOs - x is one discipline Trend: VxyO – multi-discipline virtual observatories Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

19

Selected VxyO Motivation: Mt. Spurr, AK. 8/18/1992 eruption, USGS

http://www.avo.alaska.edu/image.php?id=319 Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

20

Eruption cloud movement from Mt.Spurr, AK,1992

Deborah L. McGuinness

Semantic e-Science VancouverUSGS July 23, 2007

21

Tropopause

http://aerosols.larc.nasa.gov/volcano2.swf 22

Atmosphere Use Case 

Determine the statistical signatures of both volcanic and solar forcings on the height of the tropopause From paleoclimate researcher – Caspar Ammann – Climate and Global Dynamics Division of NCAR - CGD/NCAR Layperson perspective: - look for indicators of acid rain in the part of the atmosphere we experience… (look at measurements of sulfur dioxide in relation to sulfuric acid after volcanic eruptions at the boundary of the troposphere and the stratosphere) Nasa funded effort with Fox - NCAR, Sinha - Va. Tech, Raskin - JPL

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

23



















Use Case detail: A volcano erupts Preferentially it’s a tropical mountain (+/- 30 degrees of the equator) with ‘acidic’ magma; more SiO2, and it erupts with great intensity so that material and large amounts of gas are injected into the stratosphere. The SO2 gas converts to H2SO4 (Sulfuric Acid) + H2O (75% H2SO4 + 25% H2O). The half life of SO2 is about 30 - 40 days. The sulfuric acid condensates to little super-cooled liquid droplets. These are the volcanic aerosol that will linger around for a year or two. Brewer Dobson Circulation of the stratosphere will transport aerosol to higher latitudes. The particles generate great sunsets, most commonly first seen in fall of the respective hemisphere. The sunlight gets partially reflected, some part gets scattered in the forward direction. Result is that the direct solar beam is reduced, yet diffuse skylight increases. The scattering is responsible for the colorful sunsets as more and more of the blue wavelength are scattered away.in mid-latitudes the volcanic aerosol starts to settle, but most efficient removal from the stratosphere is through tropopause folds in the vicinity of the storm tracks. If particles get over the pole, which happens in spring of the respective hemisphere, then they will settle down and fall onto polar ice caps. Its from these ice caps that we recover annual records of sulfate flux or deposit. We get ice cores that show continuous deposition information. Nowadays we measure sulfate or SO4(2-). Earlier measurements were indirect, putting an electric current through the ice and measuring the delay. With acids present, the electric flow would be faster. What we are looking for are pulse like events with a build up over a few months (mostly in summer, when the vortex is gone), and then a decay of the peak of about 1/e in 12 months. The distribution of these pulses was found to follow an extreme value distribution (Frechet) with a heavy tail.

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

24

Use Case detail: … climate    



    

So reflection reduces the total amount of energy, forward scattering just changes the beam, path length, but that's it. The dry fogs in the sky (even after thunderstorm) still up there, thus stratosphere not troposphere. The tropical reservoir will keep delivering aerosol for about two years after the eruption. The particles are excellent scatterers in short wavelength. They do absorb in NIR and in IR. Because of absorption, there is a local temperature change in the lower stratosphere. This temperature change will cause some convective motion to further spread the aerosol, and second: Its good factual stuff. Once it warms up, it will generate a temperature gradient. Horizontal temperature gradients increase the baroclinicity and thus storms, and they speedup the local zonal winds. This change in zonal wind in high latitudes is particularly large in winter. This increased zonal wind (Westerly) will remove all cold air that tries to buildup over winter in high arctic. Therefore, the temperature anomaly in winter time is actually quite okay. Impact of volcanoes is to cool the surface through scattering of radiation. In winter time over the continents there might be some warming. In the stratosphere, the aerosol warm. The amount of GHG emitted is comparably small to the reservoir in the air. The hydrologic cycle responds to a volcanic eruption. Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

25

Atmosphere (portions from SWEET)

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

26

Atmosphere II

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

27

 



 

 

Interdisciplinary VOs, Semantics, and Explanation

Background ontologies can be used to help access and integrate distributed data sources Semantically-enabled VOs are starting to go into service (e.g., VSTO – talk later today on services and in IAAI on tues – deployed application track) Provenance issues become more critical in such systems – where did the data come from? How was it collected? Who collected it? What are their credentials? etc. Annotations and explanations may be the key to increasing trust in answers Annotations may simultaneously be a key to increasing contributions as users become confident that they will get appropriate credit An explanation interlingua (such as PML) may be a critical component to semantic integration, sharing, and acceptance An explanation infrastructure (such as Inference Web) may provide a foundation on which to build such applications

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

28

References 

IW and PML  





Trust 









Deborah L. McGuinness and Paulo Pinheiro da Silva. Explaining Answers from the Semantic Web: The Inference Web Approach. Journal of Web Semantics. Vol.1 No.4, 2004 Deborah L. McGuinness. Knowledge Representation for Question Answering. In Proceedings of the American Association for Artificial Intelligence Spring Symposium Workshop on New Directions for Question Answering. Stanford University, Stanford, CA. pages 75-77, AAAI Press, March 2003. Paulo Pinheiro da Silva, Deborah L. McGuinness and Richard Fikes. A Proof Markup Language for Semantic Web Services. Information Systems. Volume 31, Issues 4-5, 2006 (New Version – PML2 in Explanation Aware Computing Workshop at AAAI 2007. Deborah L. McGuinness, Honglei Zeng, Paulo Pinheiro da Silva, Li Ding, Dhyanesh Narayanan, and Mayukh Bhaowal. Investigations into Trust for Collaborative Information Repositories: A Wikipedia Case Study. WWW2006 Workshop on the Models of Trust for the Web (MTW'06) Ilya Zaihrayeu, Paulo Pinheiro da Silva and Deborah L. McGuinness. IWTrust: Improving User Trust in Answers from the Web. Proceedings of 3rd International Conference on Trust Management (iTrust2005) H. Zeng, M. Alhossaini, L. Ding, R. Fikes, and D. McGuinness. Computing Trust from Revision History. The 2006 International Conference on Privacy, Security and Trust (PST 2006) Honglei Zeng, Maher Alhossaini, Richard Fikes, and Deborah L. McGuinness. Mining Revision History to Assess Trustworthiness of Article Fragments. The 2nd International Conference on Collaborative Computing: Networking, Applications and Worksharing

Some particular aspects of explanation: 

 



Text Analytics: J. William Murdock, Deborah L. McGuinness, Paulo Pinheiro da Silva, Christopher Welty and David Ferrucci. Explaining Conclusions from Diverse Knowledge Sources. The 5th International Semantic Web Conference(ISWC2006) Learning Task Procedures: Deborah L. McGuinness, Alyssa Glass, Michael Wolverton and Paulo Pinheiro da Silva. Explaining Task Processing in Cognitive Assistants That Learn. FLAIRS 2007. Explaining Data Usage: Daniel J. Weitzner, Hal Abelson, Tim Berners-Lee, Chris P. Hanson, Jim Hendler, Lalana Kagal, Deborah L. McGuinness, Gerald J. Sussman, K. Krasnow Waterman. Transparent Accountable Inferencing for Privacy Risk Management. Proceedings of AAAI Spring Symposium on The Semantic Web meets eGovernment. AAAI Press, Stanford University, USA 2006. Also available as Stanford KSL Technical Report KSL06-03 and MIT CSAIL Technical Report-2006-007. User needs: Andrew. J. Cowell, Deborah L. McGuinness, Carrie F. Varley, and David A. Thurman. KnowledgeWorker Requirements for Next Generation Query Answering and Explanation Systems. In the Proceedings of the Workshop on Intelligent User Interfaces for Intelligence Analysis, International Conference on Intelligent User 29 Deborah McGuinness Semantic e-Science Vancouver July 23, 2007 Interfaces (IUIL.2006), Sydney, Australia.

Extra

Deborah L. McGuinness

Semantic e-Science Vancouver July 23, 2007

30